What is Machine Learning?

Machine Learning (ML) is a branch of AI where computers learn patterns from data, rather than following hand-written rules.

Traditional programming vs ML

Traditional:

Input:  an image
Code:   if (4 legs && tail && fur) → "dog"
Output: "dog"

You have to specify every feature. Doesn’t scale to messy real-world problems.

ML:

Input:  1 million labeled photos (dog/cat/bird/…)
Code:   "Find the patterns yourself"
Output: a model that classifies new photos at >95% accuracy

The three main flavors

1. Supervised learning

Data has labels. The model learns input → output mappings.

• Examples: spam detection, house-price prediction, face recognition.

2. Unsupervised learning

Data has no labels. The model finds structure on its own.

• Examples: customer segmentation, fraud detection, embeddings.

3. Reinforcement learning

The model tries actions in an environment and gets rewards/penalties.

• Examples: AlphaGo, robotics, RLHF for LLMs.

ML vs Deep Learning vs LLM

• ML is the broad category of learning from data
• Deep learning is ML using multi-layer neural networks
• LLM is deep learning applied to language

Who needs to know ML?

• End user: just understand the concept
• PM/marketer: know when ML beats rule-based systems
• Developer: needed if you’re building custom AI features; not needed if you’re calling LLM APIs
• Data scientist: yes, deeply

Related

• Deep Learning
• Neural Network
• Training